Exploring the two-stage approach in neural network compression for object detection

@inproceedings{Chen2019ExploringTT,
  title={Exploring the two-stage approach in neural network compression for object detection},
  author={Changqing Chen and Lixin Yu and Zhiyong Qin},
  booktitle={International Conference on Machine Vision},
  year={2019}
}
Recently, convolutional neural network (CNN) has been widely implemented in the compute vision, nature language processing and automatic driving. However, it makes much difficulties to employ the neural network in the embedded system because of the limit of memory storage and the computation bandwidth. To address those limitations, we explore a two-stage approach in neural network compression for the scene, object detection. In this paper, we first propose an effective pruning approach on a… CONTINUE READING

Results and Topics from this paper.

Key Quantitative Results

  • We utilize the two-stage model compression approach, model pruning and weights quantization, to implement on tiny-YOLO, the state-of-art object detection model, achieving total 41.9-62.7X compression rate with the accuracy loss less than 3.3%.

References

Publications referenced by this paper.
SHOWING 1-10 OF 22 REFERENCES

You Only Look Once: Unified, Real-Time Object Detection

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

YOLO9000: Better, Faster, Stronger

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Channel Pruning for Accelerating Very Deep Neural Networks

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 1 EXCERPT

Focal Loss for Dense Object Detection

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 2 EXCERPTS

Dally . Deep compression : Compressing deep neural networks with pruning , trained quantization and Huffman coding

Song Han, Huizi Mao, J. William
  • In ICLR
  • 2016

Darknet: Open source neural networks in c. http://pjreddie.com/darknet/, 2013–2016

J. Redmon
  • Proc. of SPIE Vol
  • 2016
VIEW 1 EXCERPT

Darknet: Open source neural networks in c. http://pjreddie.com/darknet/, 2013–2016

J. Redmon
  • Proc. of SPIE Vol
  • 2016
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…